© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68551
    Prev
    Next
    INDEX
    Explanations

    academic and athletic years

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is mainly detecting numeric tokens and statistics (e.g. years, counts, measurements) in sports‐career or athletic‐profile passages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    new
    -1.02
     nuove
    -1.01
    atase
    -0.99
    酐
    -0.98
     new
    -0.98
     possuem
    -0.98
     itself
    -0.95
     seventy
    -0.93
     funzioni
    -0.93
     nego
    -0.92
    POSITIVE LOGITS
     year
    1.14
     vuonna
    1.05
     senior
    1.04
     students
    1.03
     Year
    1.00
     sophomore
    0.98
     summers
    0.96
    Year
    0.95
     junior
    0.94
    چھ
    0.94
    Activations Density 0.039%

    No Known Activations